Urban employee commuting OD prediction method, system and device and medium

Abstract

The invention discloses a city employee commuting OD prediction method, system and device and a medium, and the method comprises the steps: obtaining city data, and carrying out the data processing of the city data; constructing an urban employee commuting OD prediction model, and inputting the processed urban data into the urban employee commuting OD prediction model to obtain a predicted commuting OD result; and comparing the predicted commuting OD with the actual commuting OD, and evaluating the urban employee commuting OD prediction model. According to the method, large-scale and highly regular commuting trips in conventional resident trips are selected as key points, regional population, post and housing price information is considered, an urban employee commuting OD prediction model is constructed, urban one-way commuting OD is predicted, and the urban one-way commuting OD prediction efficiency is improved. The urban employee commuting OD prediction model has the advantages of being easy in data acquisition, high in applicability, good in prediction precision, free of debugging parameters and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of urban traffic planning, and in particular relates to a method, system, device and medium for predicting OD of urban employee commuting. Background Art

[0002] With the continuous advancement of urbanization and the continuous effect of population agglomeration, urban traffic peak congestion often occurs and becomes one of the key points and difficulties of urban governance. Commuters are the main travel passenger flow during urban traffic peak hours. Rapidly and accurately predicting urban commuter OD is of great significance to the formulation of traffic planning and control strategies.

[0003] The existing urban commuter passenger flow prediction work generally adopts the "four-stage method" based on the gravity model. This method requires a lot of input data, high data acquisition cost, and a lot of parameter debugging work. To this end, many scholars at home and abroad have conducted in-depth research on travel prediction theories and methods in order to obtain a passenger flow prediction model with low input and low parameters that has promotion value. So far, relatively rich research results have been achieved, such as: radiation model, population weight opportunity model, opportunity priority selection model, location opportunity selection model, etc., focusing on abstractly describing the characteristics of urban people's travel destination selection behavior from different angles, reflecting the essence of passenger flow prediction models.

[0004] However, the research scale of existing prediction models is relatively macroscopic, focusing on obtaining the OD of all types of urban travel, and rarely considering the travel purpose of urban residents. The travel purpose is one of the main influencing factors of urban residents' travel behavior. Therefore, the present invention focuses on the commuting travel with a larger scale and stronger regularity among the regular travel of residents, and proposes a method, system, device and medium for predicting the commuting OD of urban employees. Summary of the invention

[0005] In order to overcome one or more of the above-mentioned technical defects, the present invention provides a method, system, device and medium for predicting the commuting OD of urban employees, selects the commuting trips with larger scale and stronger regularity among the regular trips of residents as the focus, considers the regional population, jobs and housing price information, constructs an OD prediction model for commuting of urban employees, and predicts the OD of one-way commuting in the city. The OD prediction model for commuting of urban employees has the advantages of easy data acquisition, strong applicability, good prediction accuracy and no debugging parameters.

[0006] In a first aspect, the present invention provides a method for predicting OD of urban workers' commuting, comprising:

[0007] Acquire urban data and process the urban data;

[0008] Construct an urban employee commuting OD prediction model, input the processed urban data into the urban employee commuting OD prediction model, and obtain the predicted commuting OD results;

[0009] The predicted commuting OD and the actual commuting OD were compared to evaluate the commuting OD prediction model for urban employees.

[0010] Furthermore, the obtaining of city data and processing of the city data include:

[0011] Obtain land use status data;

[0012] Based on the current land use data, from the perspectives of land function, all-way road network, river land distribution and administrative boundaries, the urban district (county) level administrative division data is divided into several traffic sub-districts, and several traffic sub-districts are aggregated into several traffic middle districts, where a traffic middle district includes several traffic sub-districts, and the number of traffic middle districts is less than the number of traffic sub-districts;

[0013] Obtain population data, job data and city housing price file data, where the city housing price file data includes house coordinates, house quantity and unit price information;

[0014] The traffic districts, population data, job data and urban housing price file data were analyzed to obtain the population, number of jobs and average housing price of each traffic district.

[0015] Furthermore, the obtaining of city data and processing of the city data further includes:

[0016] Obtain the city's full-mode road network data, connect the centroid of the traffic zone with several road network nodes around the traffic zone, build a physical topology network, and generate the traffic zone centroid distance matrix based on the distance between the centroids of each traffic zone.

[0017] Furthermore, the construction of the urban employee commuting OD prediction model, inputting the processed urban data into the urban employee commuting OD prediction model, and obtaining the predicted commuting OD result includes:

[0018] Based on the first selection condition, the second selection condition and the third selection condition, a commuting probability distribution formula is generated for the traffic area j to be selected as the residence by the employees of the traffic area i, where the first selection condition is that the area is closer to the workplace, the second selection condition is that the area has a larger population, and the third selection condition is that the unit housing price in the area is lower;

[0019] The population size and average housing price of the transportation community are input into the commuting probability distribution formula, and the calculated result is multiplied by the number of jobs in the transportation community to predict the commuting OD volume between transportation communities and generate a predicted commuting OD matrix.

[0020] Furthermore, the commuting probability distribution formula for generating the traffic zone j being selected as the residence by the employees of the traffic zone i based on the first selection condition, the second selection condition and the third selection condition includes:

[0021] Assume that the quality benefit of the surrounding area evaluated by the employees of the workplace is x, and the area closest to the workplace and with higher quality benefit than the workplace is selected as the residence. The quality benefit follows the random distribution f(x). When the population is used to represent the quality benefit, the first probability formula for traffic area j being selected as the residence by the employees of traffic area i is obtained:

[0022]

[0023] When housing prices are used to represent quality benefits, the second probability formula for traffic area j being chosen as a residence by employees in traffic area i is obtained:

[0024]

[0025] Combining the first probability formula and the second probability formula, the commuting probability distribution formula of traffic area j being selected as the residence by employees of traffic area i is generated:

[0026]

[0027] Furthermore, the comparison of the predicted commuting OD and the actual commuting OD to evaluate the urban employee commuting OD prediction model includes:

[0028] Obtain urban commuting OD data, aggregate urban commuting OD data into traffic zones, obtain the one-way commuting OD travel volume between each traffic zone, and generate the actual commuting OD matrix;

[0029] Sum each column of the predicted commuting OD matrix and each column of the actual commuting OD matrix respectively to obtain the predicted value of the total number of urban employees attracted by each transportation district and the true value of the total number of urban employees attracted by each transportation district, calculate the absolute value of the relative error between the predicted value and the true value, and obtain the proportion of different error scales;

[0030] The absolute value of the relative error of the same position elements of the predicted commuting OD matrix and the actual commuting OD matrix is ​​calculated, and combined with the traffic zone centroid distance matrix, the proportion of the corresponding error scale of the predicted commuting OD within different distance scales is obtained;

[0031] According to the corresponding relationship between each traffic zone and each traffic center, the predicted commuting OD and the actual commuting OD are aggregated respectively to obtain the predicted commuting OD and the actual commuting OD between each traffic center, and the corresponding error is calculated.

[0032] The second aspect of the present invention provides a city employee commuting OD prediction system, which is used to implement the above-mentioned city employee commuting OD prediction method, comprising:

[0033] A data acquisition module is used to acquire city data and process the city data;

[0034] The commuting OD prediction module is used to build a city employee commuting OD prediction model, input the processed city data into the city employee commuting OD prediction model, and obtain the predicted commuting OD results;

[0035] The evaluation module is used to compare the predicted commuting OD with the actual commuting OD and evaluate the urban employee commuting OD prediction model.

[0036] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention discloses a method, system, device and medium for predicting the commuting OD of urban employees. The method comprises the following steps: obtaining urban data and performing data processing on the urban data; constructing an urban employee commuting OD prediction model, inputting the processed urban data into the urban employee commuting OD prediction model, and obtaining a predicted commuting OD result; comparing the predicted commuting OD with the actual commuting OD, and evaluating the urban employee commuting OD prediction model; selecting commuting trips with a larger scale and a stronger regularity among regular trips of residents as the focus, considering regional population, positions and housing price information, constructing an urban employee commuting OD prediction model, and predicting the one-way commuting OD of the city. The urban employee commuting OD prediction model has the advantages of easy data acquisition, strong applicability, good prediction accuracy, and no debugging parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The specific embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings, wherein:

[0041] Figure 1 This is a flow chart of the urban employee commuting OD prediction method described in Example 1;

[0042] Figure 2 This is a flowchart of step S2 of the urban employee commuting OD prediction method described in Example 1;

[0043] Figure 3 This is a flowchart of step S3 of the urban employee commuting OD prediction method described in Example 1;

[0044] Figure 4 It is a schematic diagram of dividing traffic areas and aggregating population and job numbers in the urban employee commuting OD prediction method described in Example 1;

[0045] Figure 5 It is a schematic diagram of obtaining the distribution of housing price data information and aggregating it into traffic areas in the urban employee commuting OD prediction method described in Example 1;

[0046] Figure 6 This is a schematic diagram of reading a traffic zone file and generating a shortest distance matrix for the urban employee commuting OD prediction method described in Example 1. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0048] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0050] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0051] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "disposed" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] Example 1

[0053] This embodiment discloses a method for predicting the OD of urban workers' commuting. Figure 1 ,include:

[0054] S1. Obtain city data and process the city data.

[0055] In this embodiment, step S1 includes:

[0056] Get the current land use data. Specifically, use AutoCAD to read the current land use vector file of the local Urban Construction 2000 projection coordinate system, and use the "object alignment command" in AutoCAD to convert the land use file into the CGCS2000 projection coordinate system based on any two or more sets of coordinate corresponding points. If the current land use vector file is already in the CGCS2000 projection coordinate system, proceed directly to the next step.

[0057] Use ArcGIS to load the land use status vector file obtained in the above steps, and use the software to convert the file from the CGCS2000 projection coordinate system to the CGCS2000 geographic coordinate system. Since the difference between the CGCS2000 coordinate system and the WGS84 coordinate system is at the decimeter level, the error scale meets the OD space requirements. The land use file in the CGCS2000 geographic coordinate system can be manually changed to the WGS84 geographic coordinate system in the ArcGIS software. If the land use status vector file is already in the WGS84 geographic coordinate system, proceed directly to the next step.

[0058] Based on the land use status vector file of the WGS84 geographic coordinate system obtained in the above steps, ArcGIS is used to divide the urban district (county) level administrative division data into several traffic areas from the perspective of land function, all-way road network, river land distribution and administrative boundaries, and several traffic areas are aggregated into several traffic central areas, where one traffic central area includes several traffic areas, and the number of traffic central areas is less than the number of traffic areas.

[0059] Python is used to obtain population data and job data from the Internet, and the gcj02towgs84 function in the transbigdata package is called to convert the coordinates of the population data file and job data file into the WGS84 geographic coordinate system.

[0060] Python is used to obtain urban housing price file data from the Internet, where the urban housing price file data includes house coordinates, house quantity and unit price information. The bd09towgs84 function in transbigdata is called to convert the urban housing price file coordinates into the WGS84 geographic coordinate system.

[0061] The traffic districts, population data, job data and urban housing price file data were analyzed to obtain the population, number of jobs and average housing price of each traffic district.

[0062] In this embodiment, step S1 further includes:

[0063] By calling the graph_from_bbox function in the osmnx package in Python, we can obtain the city's full-mode road network data in the WGS84 geographic coordinate system, connect the centroid of the traffic zone with several road network nodes around the traffic zone, build a physical topology network, and generate the traffic zone centroid distance matrix based on the distance between the centroids of each traffic zone:

[0064]

[0065] Among them, D is the shortest path distance matrix between traffic cells, d ij is the shortest distance from traffic zone i to traffic zone j, and n is the number of traffic zones.

[0066] S2. Construct a city employee commuting OD prediction model, input the processed city data into the city employee commuting OD prediction model, and obtain the predicted commuting OD result.

[0067] In this embodiment, if Figure 2 , step S2 comprises:

[0068] S21. Based on the first selection condition, the second selection condition and the third selection condition, generate a commuting probability distribution formula for the traffic area j being selected as the residence by the employees of the traffic area i, wherein the first selection condition is that the area is closer to the workplace, the second selection condition is that the area has a larger population, and the third selection condition is that the unit housing price in the area is lower.

[0069] S22. Input the population and average housing price of the traffic community into the commuting probability distribution formula, multiply the calculated result by the number of jobs in the traffic community, predict the commuting OD volume between the traffic communities, and generate a predicted commuting OD matrix:

[0070] v ij =w i ×p ij (2)

[0071]

[0072] Among them, i and j are the traffic area numbers, v ij is the predicted commuting OD volume in one direction (from work to residence) between transportation zone i and transportation zone j, w i is the number of jobs in transportation community i, p ij is the probability that an urban employee whose work place is in transportation zone i chooses transportation zone j as his / her residence, and V predicts the commuting matrix.

[0073] In this embodiment, step S21 includes:

[0074] Assume that the quality benefit of the surrounding area evaluated by the employees at the workplace is x, and the area closest to the workplace and with higher quality benefit than the workplace is selected as the residence. The quality benefit follows a random distribution f(x). When the population is used to represent the quality benefit, the first probability formula (7) for the jth traffic zone to be selected as the residence by the employees of the ith traffic zone is obtained:

[0075]

[0076] Fr θ ( <x)=p(<x) θ (5)

[0077]

[0078] Combining formulas (4) to (6), we can get

[0079]

[0080] Among them, q i ,q j are the populations of traffic communities i and j, respectively, and q ij It is the sum of the populations of all transportation areas whose distance to transportation area i is less than the distance between transportation areas i and j.

[0081] When housing prices are used to represent quality benefits, since housing prices are negatively correlated with quality benefits, the second probability formula (9) that traffic community j is chosen as a place of residence by employees in traffic community i is obtained:

[0082]

[0083] Combining formulas (5), (6), and (8), we can get

[0084]

[0085] Among them, c i ,c j are the average housing prices of transportation communities i and j, c ij It is the sum of the average housing prices of all transportation communities whose distance to transportation community i is less than the distance between transportation communities i and j.

[0086] Combining formulas (7) and (9), we can generate the commuting probability distribution formula of traffic area j being selected as the residence by employees in traffic area i:

[0087]

[0088] S3. Compare the predicted commuting OD and the actual commuting OD to evaluate the urban employee commuting OD prediction model.

[0089] In this embodiment, if Figure 3 , step S3 comprises:

[0090] S31. Use Python to call the within function in the geopandas package to obtain the city commuting OD data, aggregate the city commuting OD data into traffic areas, obtain the one-way (from work to residence) commuting OD travel volume between each traffic area, and generate the actual commuting OD matrix:

[0091]

[0092] Among them, V′ is the actual commuting matrix, v i ' j It is the actual one-way commuting OD volume between transportation zone i and transportation zone j (from work to residence).

[0093] S32. Sum each column of the predicted commuting OD matrix and each column of the actual commuting OD matrix respectively to obtain the predicted value of the total number of urban employees attracted by each transportation district and the true value of the total number of urban employees attracted by each transportation district, calculate the absolute value of the relative error between the predicted value and the true value, and obtain the proportion of different error scales.

[0094]

[0095] Among them, v j is the predicted total number of employees who choose traffic zone j as their residence; v j ′ is the total number of employees who actually choose traffic zone j as their residence; r j is the absolute value of the relative error of the total number of employees who choose traffic area j as their residence; α is the error scale, which takes values ​​of 20%, 25%, ..., 45%, and 50% in turn; R α is the proportion of the number of traffic communities with a predicted total number of employees whose error is less than α to the total number; It is a 0-1 variable, which is 1 when the relative error of the prediction of the total number of employees who choose traffic community j as their residence is less than α, otherwise it is 0; n is the number of communities.

[0096] S33. By calling several functions in the numpy package in python, the absolute value of the relative error between the elements at the same position of the predicted commuting OD matrix and the actual commuting OD matrix is ​​calculated, and combined with the traffic community centroid distance matrix, the ratio of the corresponding error scale of the predicted commuting OD within different distance scales is obtained.

[0097]

[0098] Where: r ij is the absolute value of the relative error of the one-way commuting OD volume prediction from traffic area i to traffic area j; is a 0-1 variable, which is 1 when the absolute value of the relative error of the one-way commuting OD volume prediction from traffic area i to traffic area j is less than α, otherwise it is 0; δ is the distance scale, which takes values ​​of 2.5, 5, ..., 12.5, 15 (in km) respectively; is a 0-1 variable, which is 1 when the shortest path distance from traffic area i to traffic area j is less than δ, otherwise it is 0; It is the proportion of the absolute value of the predicted commuting OD relative error within the range of (δ-2.5, δ) km that is less than α.

[0099] S34. According to the corresponding relationship between each traffic zone and each traffic center, the predicted commuting OD and the actual commuting OD are aggregated respectively to obtain the predicted commuting OD and the actual commuting OD between each traffic center, and steps S32-S33 are repeated to calculate the corresponding error.

[0100] Take a city as an example. Figure 4 , call ArcGIS to divide the traffic zone and aggregate the population and job numbers; Figure 5 , call ArcGIS to read the distribution of housing price data and aggregate it into traffic areas; Figure 6 , read the traffic zone file through transCAD and generate the centroid shortest distance matrix; obtain the actual commuting data on the Internet through python and aggregate it into the traffic zone, and input the data into the urban employee commuting OD prediction model to predict the employee commuting OD results. As shown in Table 1, the total number of employees who choose traffic zone j as their place of residence has different relative error scales; as shown in Table 2, the corresponding error scale proportions under different distance scales of the predicted commuting OD; from the distribution of the prediction error results, it can be seen that this urban employee commuting OD prediction model is more suitable for medium and long distance commuting OD prediction, and the error within 30% accounts for 70%.

[0101] Table 1 Table 2

[0102] 0-2.5 2.5-5 5-7.5 7.5-10 10-12.5 12.5-15 >15 20％ 34.2％ 42.2％ 63.4％ 54.9％ 49.5％ 37.2％ 37.5％ 25％ 37.4％ 43.7％ 67.8％ 60.5％ 56.7％ 39.4％ 40.9％ 30％ 38.2％ 46.8％ 69.4％ 70.2％ 66.9％ 40.8％ 41.5％ 35％ 40.3％ 51.4％ 70.5％ 77.7％ 67.2％ 43.2％ 43.8％ 40％ 47.8％ 51.7％ 78.2％ 80.4％ 70.4％ 50.1％ 44.4％ 45％ 51.2％ 55.2％ 73.3％ 82.6％ 73.1％ 55.6％ 46.4％ 50％ 54.6％ 59.4％ 87.2％ 89.4％ 78.3％ 56.0％ 49.7％

[0103] Compared with the traditional "four-stage" OD prediction model, the method provided by the present invention is simple to operate, requires less basic data and is easier to obtain. For example, population positions can be obtained based on mobile phone signaling data or Internet location big data, and housing price data can be obtained through web crawlers. The urban employee commuting OD prediction model does not require parameter debugging, which can significantly reduce the cost and workload of passenger flow prediction.

[0104] Example 2

[0105] Based on the same inventive concept, the present embodiment discloses a city employee commuting OD prediction system. The implementation solution for solving the problem provided by the system is similar to the implementation solution recorded in the above method. Therefore, the specific limitations in one or more city employee commuting OD prediction system embodiments provided below can be referred to the above limitations on the city employee commuting OD prediction method, which will not be repeated here.

[0106] An urban employee commuting OD prediction system, comprising:

[0107] The data acquisition module is used to acquire city data and process the city data.

[0108] The commuting OD prediction module is used to build a city employee commuting OD prediction model, input the processed city data into the city employee commuting OD prediction model, and obtain the predicted commuting OD results.

[0109] The evaluation module is used to compare the predicted commuting OD with the actual commuting OD and evaluate the urban employee commuting OD prediction model.

[0110] Example 3

[0111] This embodiment discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0112] Acquire urban data and process the urban data;

[0113] Construct an urban employee commuting OD prediction model, input the processed urban data into the urban employee commuting OD prediction model, and obtain the predicted commuting OD results;

[0114] The predicted commuting OD and the actual commuting OD were compared to evaluate the commuting OD prediction model for urban employees.

[0115] In this embodiment, the processor further implements the following steps when executing the computer program:

[0116] Obtain the city's full-mode road network data, connect the centroid of the traffic zone with several road network nodes around the traffic zone, build a physical topology network, and generate the traffic zone centroid distance matrix based on the distance between the centroids of each traffic zone.

[0117] In this embodiment, the processor further implements the following steps when executing the computer program:

[0118] Based on the first selection condition, the second selection condition and the third selection condition, a commuting probability distribution formula is generated for the traffic area j to be selected as the residence by the employees of the traffic area i, where the first selection condition is that the area is closer to the workplace, the second selection condition is that the area has a larger population, and the third selection condition is that the unit housing price in the area is lower;

[0119] The population size and average housing price of the transportation community are input into the commuting probability distribution formula, and the calculated result is multiplied by the number of jobs in the transportation community to predict the commuting OD volume between transportation communities and generate a predicted commuting OD matrix.

[0120] In this embodiment, the processor further implements the following steps when executing the computer program:

[0121] Assume that the quality benefit of the surrounding area evaluated by the employees of the workplace is x, and the area closest to the workplace and with higher quality benefit than the workplace is selected as the residence. The quality benefit follows the random distribution f(x). When the population is used to represent the quality benefit, the first probability formula for traffic area j being selected as the residence by the employees of traffic area i is obtained:

[0122]

[0123] When housing prices are used to represent quality benefits, the second probability formula for traffic area j being chosen as a residence by employees in traffic area i is obtained:

[0124]

[0125] Combining the first probability formula and the second probability formula, the commuting probability distribution formula of traffic area j being selected as the residence by employees of traffic area i is generated:

[0126]

[0127] In this embodiment, the processor further implements the following steps when executing the computer program:

[0128] Obtain urban commuting OD data, aggregate urban commuting OD data into traffic zones, obtain the one-way commuting OD travel volume between each traffic zone, and generate the actual commuting OD matrix;

[0129] Sum each column of the predicted commuting OD matrix and each column of the actual commuting OD matrix respectively to obtain the predicted value of the total number of urban employees attracted by each transportation district and the true value of the total number of urban employees attracted by each transportation district, calculate the absolute value of the relative error between the predicted value and the true value, and obtain the proportion of different error scales;

[0130] The absolute value of the relative error of the same position elements of the predicted commuting OD matrix and the actual commuting OD matrix is ​​calculated, and combined with the traffic zone centroid distance matrix, the proportion of the corresponding error scale of the predicted commuting OD within different distance scales is obtained;

[0131] According to the corresponding relationship between each traffic zone and each traffic center, the predicted commuting OD and the actual commuting OD are aggregated respectively to obtain the predicted commuting OD and the actual commuting OD between each traffic center, and the corresponding error is calculated.

[0132] Example 4

[0133] This embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0134] Acquire urban data and process the urban data;

[0135] Construct an urban employee commuting OD prediction model, input the processed urban data into the urban employee commuting OD prediction model, and obtain the predicted commuting OD results;

[0136] The predicted commuting OD and the actual commuting OD were compared to evaluate the commuting OD prediction model for urban employees.

[0137] In this embodiment, when the computer program is executed by the processor, the following steps are also implemented:

[0138] Obtain the city's full-mode road network data, connect the centroid of the traffic zone with several road network nodes around the traffic zone, build a physical topology network, and generate the traffic zone centroid distance matrix based on the distance between the centroids of each traffic zone.

[0139] In this embodiment, when the computer program is executed by the processor, the following steps are also implemented:

[0140] Based on the first selection condition, the second selection condition and the third selection condition, a commuting probability distribution formula is generated for the traffic area j to be selected as the residence by the employees of the traffic area i, where the first selection condition is that the area is closer to the workplace, the second selection condition is that the area has a larger population, and the third selection condition is that the unit housing price in the area is lower;

[0141] The population size and average housing price of the transportation community are input into the commuting probability distribution formula, and the calculated result is multiplied by the number of jobs in the transportation community to predict the commuting OD volume between transportation communities and generate a predicted commuting OD matrix.

[0142] In this embodiment, when the computer program is executed by the processor, the following steps are also implemented:

[0143] Assume that the quality benefit of the surrounding area evaluated by the employees of the workplace is x, and the area closest to the workplace and with higher quality benefit than the workplace is selected as the residence. The quality benefit follows the random distribution f(x). When the population is used to represent the quality benefit, the first probability formula for traffic area j being selected as the residence by the employees of traffic area i is obtained:

[0144]

[0145] When housing prices are used to represent quality benefits, the second probability formula for traffic area j being chosen as a residence by employees in traffic area i is obtained:

[0146]

[0147] Combining the first probability formula and the second probability formula, the commuting probability distribution formula of traffic area j being selected as the residence by employees of traffic area i is generated:

[0148]

[0149] In this embodiment, the processor further implements the following steps when executing the computer program:

[0150] Obtain urban commuting OD data, aggregate urban commuting OD data into traffic zones, obtain the one-way commuting OD travel volume between each traffic zone, and generate the actual commuting OD matrix;

[0151] Sum each column of the predicted commuting OD matrix and each column of the actual commuting OD matrix respectively to obtain the predicted value of the total number of urban employees attracted by each transportation district and the true value of the total number of urban employees attracted by each transportation district, calculate the absolute value of the relative error between the predicted value and the true value, and obtain the proportion of different error scales;

[0152] The absolute value of the relative error of the same position elements of the predicted commuting OD matrix and the actual commuting OD matrix is ​​calculated, and combined with the traffic zone centroid distance matrix, the proportion of the corresponding error scale of the predicted commuting OD within different distance scales is obtained;

[0153] According to the corresponding relationship between each traffic zone and each traffic center, the predicted commuting OD and the actual commuting OD are aggregated respectively to obtain the predicted commuting OD and the actual commuting OD between each traffic center, and the corresponding error is calculated.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0155] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Therefore, any modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the technical solution of the present invention shall still fall within the scope of the technical solution of the present invention.

Claims

1. A method for predicting OD of urban workers' commuting, characterized in that: include: Acquire urban data and process the urban data; Construct an urban employee commuting OD prediction model, input the processed urban data into the urban employee commuting OD prediction model, and obtain the predicted commuting OD results; The predicted commuting OD and the actual commuting OD were compared to evaluate the commuting OD prediction model for urban employees.

2. The urban employee commuting OD prediction method according to claim 1 is characterized in that: The obtaining of city data and processing of the city data include: Obtain land use status data; Based on the current land use data, from the perspectives of land function, all-way road network, river land distribution and administrative boundaries, the urban district (county) level administrative division data is divided into several traffic sub-districts, and several traffic sub-districts are aggregated into several traffic middle districts, where a traffic middle district includes several traffic sub-districts, and the number of traffic middle districts is less than the number of traffic sub-districts; Obtain population data, job data and city housing price file data, where the city housing price file data includes house coordinates, house quantity and unit price information; The traffic districts, population data, job data and urban housing price file data were analyzed to obtain the population, number of jobs and average housing price of each traffic district.

3. The urban employee commuting OD prediction method according to claim 2 is characterized in that: The step of obtaining the city data and processing the city data further includes: Obtain the city's full-mode road network data, connect the centroid of the traffic zone with several road network nodes around the traffic zone, build a physical topology network, and generate the traffic zone centroid distance matrix based on the distance between the centroids of each traffic zone.

4. The urban employee commuting OD prediction method according to claim 2 is characterized in that: The step of constructing a city employee commuting OD prediction model and inputting the processed city data into the city employee commuting OD prediction model to obtain a predicted commuting OD result includes: Based on the first selection condition, the second selection condition and the third selection condition, a commuting probability distribution formula is generated for the traffic area j to be selected as the residence by the employees of the traffic area i, where the first selection condition is that the area is closer to the workplace, the second selection condition is that the area has a larger population, and the third selection condition is that the unit housing price in the area is lower; The population size and average housing price of the transportation community are input into the commuting probability distribution formula, and the calculated result is multiplied by the number of jobs in the transportation community to predict the commuting OD volume between transportation communities and generate a predicted commuting OD matrix.

5. The urban employee commuting OD prediction method according to claim 1 is characterized in that: The commuting probability distribution formula for generating the traffic zone j being selected as the residence by the employees of the traffic zone i based on the first selection condition, the second selection condition and the third selection condition includes: Assume that the quality benefit of the surrounding area evaluated by the employees of the workplace is x, and the area closest to the workplace and with higher quality benefit than the workplace is selected as the residence. The quality benefit follows the random distribution f(x). When the population is used to represent the quality benefit, the first probability formula for traffic area j being selected as the residence by the employees of traffic area i is obtained: When housing prices are used to represent quality benefits, the second probability formula for traffic area j being selected as a residence by employees in traffic area i is obtained: Combining the first probability formula and the second probability formula, the commuting probability distribution formula of traffic area j being selected as the residence by employees of traffic area i is generated:

6. The urban employee commuting OD prediction method according to claim 1 is characterized in that: The comparison between the predicted commuting OD and the actual commuting OD and the evaluation of the urban employee commuting OD prediction model include: Obtain urban commuting OD data, aggregate urban commuting OD data into traffic zones, obtain the one-way commuting OD travel volume between each traffic zone, and generate the actual commuting OD matrix; Sum each column of the predicted commuting OD matrix and each column of the actual commuting OD matrix respectively to obtain the predicted value of the total number of urban employees attracted by each transportation district and the true value of the total number of urban employees attracted by each transportation district, calculate the absolute value of the relative error between the predicted value and the true value, and obtain the proportion of different error scales; The absolute value of the relative error of the same position elements of the predicted commuting OD matrix and the actual commuting OD matrix is ​​calculated, and combined with the traffic zone centroid distance matrix, the proportion of the corresponding error scale of the predicted commuting OD within different distance scales is obtained; According to the corresponding relationship between each traffic zone and each traffic center, the predicted commuting OD and the actual commuting OD are aggregated respectively to obtain the predicted commuting OD and the actual commuting OD between each traffic center, and the corresponding error is calculated.

7. A city employee commuting OD prediction system, used to implement the city employee commuting OD prediction method according to claims 1-6, characterized in that: include: A data acquisition module is used to acquire city data and process the city data; The commuting OD prediction module is used to build a city employee commuting OD prediction model, input the processed city data into the city employee commuting OD prediction model, and obtain the predicted commuting OD results; The evaluation module is used to compare the predicted commuting OD with the actual commuting OD and evaluate the urban employee commuting OD prediction model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images